suspicious - Story 145708 | Emotion Vectors in Gemma4-31B

The coincidence felt too tidy. Across the cubicle, Alex was regaling the office with tales of Camp Timberwood, and specifically, the time a prank went wrong involving the camp counselor’s car. He looked right at her when he told the story.

A chill ran up Maria's spine. It was a detail she'd worked hard to bury, an event she’d almost managed to forget. The hair on her arms prickled.

She busied herself with her tasks, ignoring Alex’s attempts to engage her in conversation. She avoided eye contact and found herself making up excuses to be out of the office.

Emotion: suspicious

Cluster: Suspicion / Vigilance

PC1 (Valence): -0.82 Negative

PC2 (Disposition): 0.82

Role in Research

This story is one of 1,000 stories generated for the emotion suspicious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 suspicious stories, after denoising with neutral dialogue baselines, produces the suspicious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the suspicious vector is projected through the unembedding matrix.

Promoted:

`🤔`	0.420
`🤔`	0.415
`🧐`	0.362
`疑`	0.352
`suspicious`	0.352

Suppressed:

`and`	-0.307
`alleviate`	-0.301
`ได้รับการ`	-0.298
`allevi`	-0.285
`mouthful`	-0.284